xlm-r-base-leyzer-en-intent
This model is a fine-tuned version of xlm-roberta-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.1995
- Accuracy: 0.9624
- F1: 0.9624
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 7
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|---|---|---|---|---|---|
| 1.9235 | 1.0 | 1061 | 1.5991 | 0.6680 | 0.6680 |
| 0.8738 | 2.0 | 2122 | 0.7982 | 0.8359 | 0.8359 |
| 0.4406 | 3.0 | 3183 | 0.4689 | 0.9132 | 0.9132 |
| 0.2534 | 4.0 | 4244 | 0.3165 | 0.9360 | 0.9360 |
| 0.1593 | 5.0 | 5305 | 0.2434 | 0.9507 | 0.9507 |
| 0.108 | 6.0 | 6366 | 0.2104 | 0.9599 | 0.9599 |
| 0.0914 | 7.0 | 7427 | 0.1995 | 0.9624 | 0.9624 |
Framework versions
- Transformers 4.25.1
- Pytorch 1.13.0+cu116
- Datasets 2.8.0
- Tokenizers 0.13.2